chore(meta): update changelog

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

CHANGELOG.md

@@ -7,6 +7,16 @@ Format based on [Keep a Changelog](https://keepachangelog.com/).
 ## [Unreleased]
 
 ### Added
+- Round 17 content architecture workshop — Full team (8 agents, 3 rounds) defining content pipeline
+- D-023: Three-tier content model (authored drama modules, templated content, procedural filler) with life-sim substrate
+- D-024: NPC generation model — 10 axes (7 essential + 3 supporting) with CombatCapability ECS component
+- D-025: Social site / functional cluster as atomic Tier 2 template unit (4-8 NPCs, 15-40 tiles)
+- D-026: Simulation tiers with timestamp-based LRU eviction (Active/Background/State-saved/Ungenerated)
+- D-027: Vertical slice — smuggler + detective two-character proof-of-concept (supersedes D-006)
+- D-028: Dialogue architecture — tagged line pools with four relational layers (access tiers, history, trust-gating, unprompted disclosure)
+- D-029: Population entanglement ratio — 30% flat / 50% mundane triangles / 20% intrigue-entangled
+- Content architecture workshop brief documenting the "life first, drama second" design philosophy
+- Mellanie (Copywriter) activated from standby for content authoring phase
 - Round 16 faction development — Full faction framework with lore, political analysis, mechanical grounding (session closed, awaiting team input for v0.1 selection)
 - 3D reputation system: Trust × Usefulness × Exposure per faction
 - Faction mechanical grounding: starting loadouts, information asymmetry, blind spots, resource loops

DECISIONS.md

@@ -37,11 +37,12 @@ This document tracks confirmed decisions, open questions, and rejected alternati
 - **Raised by:** Team Leader (Jeroen), evolved through Rounds 4-6 with full team input.
 - **Dissent:** None. Team unanimously energized by the pivot.
 
-### D-006: Prototype scenario - Institute / Armstrong City / Guardians
+### D-006: SUPERSEDED by D-027
 - **Date:** 2026-02-08
 - **Decision:** The first playable prototype focuses on the Starflyer conspiracy arc, scoped to the investigative/political hub: the Institute, Armstrong City, and the Guardians of Selfhood. This tests the core mechanic (asymmetric information in a conspiracy) with controllable scope.
 - **Rationale:** The conspiracy arc IS asymmetric information. If it's not compelling at this scale, a galaxy won't fix it. If it works, everything else is expansion.
 - **Raised by:** Team Leader (Jeroen).
+- **Superseded by:** D-027 (smuggler + detective vertical slice, 2026-02-10)
 
 ### D-007: Five pillars of game design
 - **Date:** 2026-02-08
@@ -278,6 +279,56 @@ This document tracks confirmed decisions, open questions, and rejected alternati
 - **Dissent:** None.
 - **Effective:** Immediately (Round 15 onward).
 
+### D-023: Three-tier content model with life-sim substrate
+- **Date:** 2026-02-10
+- **Decision:** The game uses a three-tier content architecture: Tier 1 (authored drama modules drawn from a pool at game start — plural, optional, relocatable), Tier 2 (templated content with combinatorial variation — both intrigue and life templates), Tier 3 (procedural filler with systemic hooks for Tier 2 colonization). Daily life is the substrate; conspiracies are weather. Players can investigate, pursue careers/relationships, or both. All are valid playthroughs. The storyteller activates Tier 1 modules based on player proximity and engagement, not timers.
+- **Rationale:** A galaxy-spanning game needs content architecture that scales without hand-crafting everything. The life-sim substrate creates attachment that gives conspiracies emotional weight. Pool-based Tier 1 modules enable replayability and DLC expansion.
+- **Raised by:** Team Leader (Jeroen), with full team endorsement across 3 rounds
+- **Dissent:** None
+
+### D-024: NPC generation model — 10 axes + combat component
+- **Date:** 2026-02-10
+- **Decision:** NPCs are generated with 10 axes: 7 essential (Want, Secret/vulnerability, Relationships 1-3, Tolerance threshold, Daily routine, Information inventory, Contentment) and 3 supporting (Personality traits 2-3, Tell system, Skill set including combat tag). Combat capability lives as an optional CombatCapability ECS component triggered by the combat-trained skill tag, not as an axis. Faction loyalty is folded into Relationships+Secret (discoverable, not labeled). Romantic profile is folded into Want+Personality+compatibility tag. Cultural/origin template is generation-time flavor, not a runtime axis. Triangles (3 NPCs with conflicting interests) are the atomic unit of social intrigue — 2 per template minimum, 1 cross-template.
+- **Rationale:** Axes that create contradictions within NPCs produce player decisions. The 5 key interactions (Want×Secret, Routine×Secret, Tolerance×Relationships, Want×Relationships, Personality×Tolerance) drive the full investigation-and-social gameplay loop. Contentment axis (proposed by Gore) connects generated NPCs to the thematic spine. Combat as component follows the same pattern as perception modes (D-017).
+- **Raised by:** Gestalt (consolidation), Gore (contentment axis), Paula (triangle model), Tyre (combat component). Full team endorsed.
+- **Dissent:** None
+
+### D-025: Social site / functional cluster as atomic template unit
+- **Date:** 2026-02-10
+- **Decision:** The atomic Tier 2 template unit is a "social site" (mechanical term) housed in a "functional cluster" (spatial term): 4-8 NPCs who regularly interact, within 15-40 tiles of connected space with internal sightlines. Social group defines systemic identity (who, what triangles). Physical cluster defines spatial identity (sightlines, overhearing, public/private). Templates define roles; NPCs fill roles. One NPC can hold roles in multiple social sites. NPC identity is independent of template instantiation. NPCs are owned by exactly one template with reference links (carrying relationship metadata) to others.
+- **Rationale:** Life in the Settled Reach happens in clusters of connected spaces. The functional cluster is the natural unit of social observation, which is the natural unit of gameplay. Single-ownership with reference links prevents lifecycle conflicts while enabling cross-template contamination.
+- **Raised by:** Gestalt (social site), Miri (functional cluster), Tyre (ownership model), Paula (reference metadata)
+- **Dissent:** None
+
+### D-026: Simulation tiers with timestamp-based eviction
+- **Date:** 2026-02-10
+- **Decision:** Four simulation tiers: Active (30-80 NPCs, full sim at 10-20 ticks/sec), Background (500-2,000 NPCs, state machine ticks 1/game-minute with 4 machines: schedule, mood, relationships, job), State-saved (10,000+, frozen serialized structs ~1-2KB each), Ungenerated (doesn't exist yet). Eviction uses interaction-timestamp LRU against available sim-space. NPCs with active scope tags (neighborhood, active-quest, colleague, known-contact) stay fully simulated. State-saved NPCs reactivate on player return (~2-5ms). Density follows the player — content generated ahead of arrival, home system fully instantiated at game start.
+- **Rationale:** Timestamp-based eviction replaces categorical persistence rules with one priority queue. State-save makes disposal reversible. bevy_ecs dynamic component add/remove makes tier transitions seamless. Tyre confirmed all proposals fit within performance budgets.
+- **Raised by:** Team Leader (timestamp model), Tyre (technical validation), Gestalt (scope tags)
+- **Dissent:** None
+
+### D-027: Vertical slice — smuggler + detective, two-character proof
+- **Date:** 2026-02-10
+- **Decision:** The proof-of-concept vertical slice is one station district containing: 1 workplace social site, 1 social venue (bar), 1 smuggling ring template, shared NPCs. Two playable characters: smuggler (logistics worker, insider access to criminal templates, social camouflage) and detective (institutional investigator, authority access, analytical). Success criteria: (1) 30 minutes of daily-life breathing room before contamination activates, (2) both playthroughs feel like fundamentally different games, (3) after each playthrough player names an NPC they felt conflicted about, (4) the observe→notice→follow→discover sequence emerges from systems not scripts.
+- **Supersedes:** D-006 (prototype scenario: Institute/Armstrong/Guardians)
+- **Rationale:** Smuggler + detective creates adversarial divergence — the detective's target IS the smuggler's daily life. Same templates, same NPCs, inverted relationships. Proves character-as-lens, contamination, life-sim attachment, and replayability simultaneously. Tyre confirms: ~20% more effort than single-character, no new architecture.
+- **Raised by:** Team Leader (smuggler+detective choice), Nigel (two-character requirement), Ozzie (30-min runway), Gore (emotional criterion), Gestalt (systems criterion)
+- **Dissent:** None
+
+### D-028: Dialogue architecture — tagged line pools with four relational layers
+- **Date:** 2026-02-10
+- **Decision:** Dialogue uses tagged line pools with systemic selection, not branching trees. Four relational layers, all planned from authoring day one, built in sequence: (1) Access tiers — insider/outsider/authority/peer filter on every line, (2) Relationship history — interaction log modifying greeting and topic selection, (3) Trust-gated gossip — three disclosure tiers per role (surface/real/secret), (4) Unprompted disclosure — NPCs volunteer information weighted by trust and mood. Trait modifiers (not per-trait scripts) reshape delivery — base lines + trait transformation guide per template. Template content packs as writing deliverable: role voice kits, situation scripts, monologue hooks, environmental text, trait transformation guide. ~165-210 authored lines per Tier 2 template, generation-expanded 4x. Social dialogue budgeted 40% more than investigation. Line previewer CLI required as authoring tool and regression test harness.
+- **Rationale:** All four layers are load-bearing — each enriches the previous ones. Tagged pools avoid combinatorial explosion while trait modifiers produce character variety. The generation pass (write 10, generate 40) scales authored content. Every memorable line needs a human hand; the generation pass fills the background.
+- **Raised by:** Mellanie (authoring model), Paula (relational layers), Gestalt (axis-to-pipeline mapping), Tyre (previewer feasibility)
+- **Dissent:** None on model. Minor ordering difference: Mellanie front-loads access tiers (structural), Paula front-loads relationship history (narrative). Both sequences work.
+
+### D-029: Population entanglement ratio — 30/50/20
+- **Date:** 2026-02-10
+- **Decision:** NPC population split: ~30% truly flat (routine + greeting, social wallpaper), ~50% mundane triangles (neighbor disputes, workplace rivalries, relationship tensions — no conspiracy connection), ~20% entangled with intrigue content. The entanglement rate varies per seed to prevent metagaming calibration. Module attachment to known NPCs uses a ~60-70/30-40 ratio (known vs stranger), also varying per seed. The unentangled majority is both thematically essential ("is this enough?" needs honest counterweight) and mechanically essential (investigation signal requires noise floor).
+- **Rationale:** If every NPC is suspicious, investigation collapses. The mundane triangles ARE the life-sim game — hours of play that never touch conspiracy. Variable entanglement rate defeats metagaming across playthroughs. Quiet life must feel genuinely good, not empty.
+- **Raised by:** Gore (thematic), Paula (30/50/20 split), Nigel (anti-metagaming), Team Leader (majority unentangled)
+- **Dissent:** None
+
 ### D-004: Team composition confirmed
 - **Date:** 2026-02-08
 - **Decision:** Team of 8 agents + Team Leader.

docs/discussions/README.md

@@ -20,3 +20,4 @@ Historical discussion rounds from the Commonwealth game design process.
 | 14 | Setting Foundation — The Settled Reach | D-021 | [round-14](round-14-worldbuilding-settled-reach.md) |
 | 15 | README / Steam Page Placeholder | - | [round-15](round-15-readme-steam-page.md) |
 | 16 | Factions — Building a Fuller Narrative Picture | AWAITING INPUT | [complete](round-16-factions-complete.md), [lore](round-16-factions.md), [mechanics](round-16-faction-mechanics.md), [notes](round-16-session-notes.md) |
+| 17 | Content Architecture | D-023, D-024, D-025, D-026, D-027, D-028, D-029 | [round-17](round-17-content-architecture.md) |

docs/workshops/content-architecture-workshop-brief.md

@@ -0,0 +1,266 @@
+# Workshop Brief: Content Architecture
+## Filling a Galaxy Without Emptiness
+
+**Project:** The Settled Reach (D-021)
+**Date:** 2026-02-10
+**Called by:** Jeroen
+**Participants:** MIRI, OZZIE, PAULA, GORE, GESTALT, NIGEL, TYRE, MELLANIE
+
+---
+
+## The Problem
+
+The Settled Reach spans hundreds of star systems connected by alien gates. Players explore with unlimited scrolling maps. If most of that space is empty or repetitive, the game feels dead. If we hand-craft everything, we'll ship in 2045. We need an architecture that makes the galaxy feel inhabited, varied, and worth exploring — built from a manageable amount of authored content amplified by procedural generation and systemic interaction.
+
+---
+
+## The Reframe: Life First, Drama Second
+
+The original pitch framed the game around a single conspiracy the player investigates. We're proposing a fundamental shift: **daily life is the substrate, and conspiracies are weather.**
+
+A player should be able to live a life — hold a job, rent an apartment, upgrade to a house, go on dates, hook up, build routines, have a local bar. That lived experience is what makes everything else matter. You don't care about a conspiracy threatening gate infrastructure unless you commute through that gate. Political intrigue hits different when your partner's employer is connected. Combat is terrifying because you have something to lose beyond a mission objective.
+
+Conspiracies become **Tier 1 modules drawn from a pool at game start** — multiple of them, coexisting, activating based on the storyteller's read of the player's life. The player might engage with one, stumble into another, or ignore them all and focus on getting promoted at work. All are valid playthroughs.
+
+This means the Senator doesn't start the game investigating a conspiracy — she starts the game *being a senator*. The conspiracy finds her because she's doing her job and notices irregularities. The Guardian finds something wrong because they're protecting someone. Or the player ignores every thread and dates the bartender. That's fine. The storyteller adjusts.
+
+**Design consequence:** We need Tier 2 templates for mundane life systems (workplaces, housing, social venues, dating, commerce) alongside the intrigue templates. The mundane layer is simpler per-template but must interlock systemically — your job pays rent, your neighborhood determines who you meet, your social life creates exposure to information.
+
+---
+
+## Proposed Architecture: Three Content Tiers
+
+### Tier 1 — Authored Drama Modules (Pool, Not Spine)
+
+Major narrative arcs: conspiracies, faction wars, gate crises, political upheavals, first-contact scenarios. Fully authored with maximum narrative weight, but designed as **relocatable, optional, and plural.**
+
+- Multiple Tier 1 modules are drawn from a pool at game start
+- Each module has a structure (who's involved, what's at stake, how it escalates) but slots into randomized geography and NPCs
+- Modules activate based on the storyteller's assessment of player proximity and engagement — not on a timer
+- A module can escalate in the background if the player ignores it, creating consequences that ripple into daily life
+- Key NPCs are authored characters with full dialogue, arcs, and secrets
+- Hooks connect downward into Tier 2 content and sideways into other Tier 1 modules
+
+**Critical shift:** No module is mandatory. The player's story might be about uncovering a galaxy-spanning conspiracy, or it might be about clawing their way from a dead-end security job to owning a bar on a gate station. Both are real games.
+
+**Budget reality:** This is highest-cost content. Every Tier 1 module needs to justify its authoring investment with replayability across character perspectives and the understanding that some players may never engage with it.
+
+### Tier 2 — Templated Content with Combinatorial Variation
+
+The workhorse layer. Authored **archetypes** that define a situation, a cast of roles, possible complications, and connection hooks — then get populated with generated NPCs and randomized variables at instantiation.
+
+#### Intrigue Templates (investigation, conflict, power)
+- Smuggling ring operating through a gate corridor
+- Corporate research outpost with an ethics problem
+- Failing colony with a resource dispute
+- Black market near a gate chokepoint
+- Dissident cell inside a faction hub
+- Abandoned facility with salvage and hazards
+
+#### Life Templates (work, home, social, commerce)
+- Workplace with a boss, colleagues, politics, and a career ladder
+- Residential block with neighbors, landlords, and local dynamics
+- Social venue (bar, club, gym, park) with regulars and social opportunities
+- Market/commercial district with merchants, services, and economic activity
+- Dating/relationship dynamics with attraction, compatibility, and relationship progression
+- Local governance or community board with petty disputes and real stakes
+
+Each template defines:
+- **Roles** (not specific NPCs): the boss, the informant, the muscle, the reluctant participant — or the landlord, the neighbor, the romantic interest, the rival
+- **Complications** (randomized): internal betrayal, external pressure, time bomb, competing interests — or rent increase, workplace drama, romantic competition, neighborhood dispute
+- **Environmental variations:** station, surface, orbital, underground
+- **Hooks:** connections to Tier 1 modules, other Tier 2 templates, or player actions
+- **Escalation paths:** what happens if the player engages deeply vs. ignores vs. makes things worse
+
+**Scale target for discussion:** 40–60 templates total (split roughly 60/40 between intrigue and life), with 3–5 major variations each. 15–20 for a vertical slice including at least 3–4 life templates.
+
+**Key interlock:** Life templates and intrigue templates must be able to contaminate each other. Your workplace colleague turns out to be connected to a smuggling ring. Your date works at the facility where something is wrong. The mundane and the dramatic share NPCs, locations, and systemic hooks.
+
+### Tier 3 — Procedural Filler That Knows Its Role
+
+Transit corridors, minor settlements, resource nodes, ambient traffic, background infrastructure. This layer doesn't try to be interesting on its own — it tries to be **plausible**.
+
+- Gate corridors with cargo haulers and customs checkpoints
+- Residential districts with foot traffic and ambient life
+- Industrial zones, docking facilities, maintenance tunnels
+- Environments that exist for systemic reasons, not narrative ones
+
+**Critical design rule:** Tier 3 content must have systemic hooks so that Tier 2 or Tier 1 content can **colonize** it when needed. An empty waystation becomes interesting the moment a Tier 2 smuggling template drops an NPC there. A generic apartment block becomes home when the player signs a lease.
+
+---
+
+## DLC and Expansion Architecture
+
+The pool-based Tier 1 design is inherently DLC-ready. If conspiracies, life paths, and drama arcs are modules drawn from a pool, **expanding the pool is the DLC model.**
+
+### What DLC Looks Like at Each Tier
+
+| Tier | Base Game | DLC Expansion |
+|------|-----------|---------------|
+| **Tier 1** | 3–5 conspiracy/drama modules in the pool | New modules: a gate builder first-contact arc, a civil war, an AI uprising, a new career path like piracy or politics |
+| **Tier 2** | 40–60 templates (intrigue + life) | New template packs: new workplace types, new criminal enterprises, new relationship dynamics, region-specific templates |
+| **Tier 3** | Procedural filler for core galaxy | New biomes, station types, environmental hazards, cultural variations for new regions |
+| **Characters** | Base roster of playable characters | New characters with new starting positions, new perception modes, new professional access |
+| **Regions** | Core Settled Reach systems | New gate clusters, frontier regions, contested zones with their own Tier 2/3 libraries |
+
+### Design Principles for DLC-Readiness
+
+- **Tier 1 modules must be self-contained with standardized connection interfaces.** A DLC conspiracy module plugs into the same storyteller hooks as a base game one. No special-casing.
+- **Tier 2 templates must be taggable by region/theme/expansion.** The storyteller draws from whatever pools are installed. If the player owns the "Frontier Expansion," frontier templates enter the draw.
+- **New characters are the premium DLC play.** A new character means a new perspective on the entire existing galaxy — every Tier 1 and Tier 2 module looks different from their position. High perceived value, moderate authoring cost since the world already exists.
+- **Region expansions are the big content drops.** New star systems with their own Tier 2 template libraries, local factions, and at least one Tier 1 module. These extend the galaxy map itself.
+- **Life path expansions are the sleeper hit.** New career tracks, new relationship types, new housing options, new social systems. Players who want to *live in* the game will pay for more ways to do it.
+
+### What This Means for Base Game Scope
+
+The base game needs to ship with enough content to be a complete experience, but the architecture should never assume the pool is closed. Specifically:
+- The storyteller's module-drawing logic must handle variable pool sizes gracefully
+- Template IDs and hook interfaces need to be stable and versioned from day one
+- Save games must handle missing DLC (player uninstalls an expansion — what happens to content generated from those templates?)
+- Modding support becomes a natural extension: if templates have a standardized format, community-authored templates can enter the pool
+
+---
+
+## Key Design Principle: Density Follows the Player
+
+Don't fill the galaxy uniformly. The storyteller AI seeds and activates Tier 2 content in the player's path and periphery.
+
+- Systems the player never visits stay as Tier 3 sketches
+- Systems the player is approaching get Tier 2 templates instantiated ahead of arrival
+- NPCs in newly instantiated content get backstories and local relationships generated with enough lead time to feel established
+- The player's information asymmetry is our alibi — they can never prove a location was barren five minutes ago
+- **Life systems instantiate around the player's home base with higher density and persistence** — your neighborhood needs to feel stable even if the far side of the galaxy is procedural fog
+
+This is **lazy generation justified by the core mechanic**. The fog of war isn't hiding empty space — it's hiding content that hasn't been generated yet.
+
+### Simulation Budget and the Offscreen Problem
+
+Not everything needs full simulation. When a player asks the bartender on a date, the system doesn't need to have been simulating the bartender's love life for 40 hours. It needs to **generate a plausible state on demand** and act like it was always there.
+
+Proposed simulation tiers:
+- **Active (player-proximate):** Full behavior simulation, real-time reactions, observable tells
+- **Background (player's home system, known NPCs):** Lightweight state updates on a tick — relationship drift, job changes, mood shifts. Enough that things feel alive when the player returns
+- **Dormant (everything else):** Frozen until the player approaches, then state-forwarded to current time based on NPC axes and template rules
+- **Ungenerated:** Doesn't exist yet. Tier 3 placeholder. Instantiated when needed.
+
+The hard question for TYRE: what's the NPC count ceiling for "Background" tier simulation, and what tick rate is sustainable?
+
+---
+
+## NPC Generation Model
+
+Inspired by Rimworld's pawn system: NPCs feel alive not because they're deep, but because their trait combinations create emergent stories. A nervous doctor with a gambling problem and a grudge against their supervisor writes its own narrative from systemic interaction alone.
+
+### Proposed NPC Axes (8–12 per character)
+
+| Axis | What It Does | Example |
+|------|-------------|---------|
+| **Personality traits** (2–3) | Drives behavior and dialogue selection | Cautious, gregarious, vindictive |
+| **Faction loyalty** | Determines allegiance and information access | Commonwealth loyalist / secretly compromised |
+| **A secret or vulnerability** | Creates leverage and investigation targets | Gambling debt, undisclosed augmentation, past crime |
+| **A want** | Motivates actions the player can exploit or assist | Promotion, escape, revenge, money, love, stability |
+| **Relationships** (1–3) | Connects NPCs into webs | Owes a debt to X, romantically involved with Y, fears Z |
+| **Skill set** | Determines what they can do in simulation | Medical, technical, combat, social, political |
+| **Tolerance threshold** | When they flip, break, run, or fight | How much pressure before behavior changes |
+| **Cultural/origin template** | Name, speech patterns, background flavor | Colony-born, gate-city cosmopolitan, military veteran |
+| **Tell system** | Observable behavioral markers tied to traits | Nervous fidgeting, over-formal speech, avoids eye contact |
+| **Information inventory** | What they know and what they'll share | Knows about the shipment but won't mention it unless pressed |
+| **Romantic/social profile** | Attraction patterns, relationship style, availability | Who they're drawn to, how they express interest, dealbreakers |
+| **Daily routine** | Where they go and when | Work schedule, social habits, commute patterns — observable by the player |
+
+### Generation Rules
+- When a Tier 2 template instantiates, its 4–8 NPCs get **internal relationships first**, then optional weak ties to NPCs in adjacent locations
+- Traits must actually affect behavior in simulation, not just flavor text
+- The "tell" system is gameplay-critical: players detect personality through observation, not character sheets
+- Backstory is assembled from a pool of life-event fragments connected logically (born on X, worked as Y, ended up here because Z)
+- Name generation follows cultural/faction templates
+- **Romantic/social axes must interact with personality and wants** — a vindictive NPC who wants stability and is drawn to the player creates a very different relationship than a gregarious NPC who wants escape
+- **Daily routines create observable patterns** that reward player attention and enable both investigation and social play
+
+---
+
+## Architectural Fit
+
+Our client-server architecture supports this naturally:
+
+- **Rust simulation server** handles content generation, NPC simulation, and state management across simulation tiers
+- **Client only sees** what's in the player's perception range
+- Server can spin up and tear down simulation detail based on player proximity
+- **Godot client** renders whatever the server says exists — no client-side world state to maintain
+- Content generation is a server-side concern invisible to the player
+- **DLC modules are server-side data** — new template definitions, new Tier 1 module scripts, new NPC axis values. The engine doesn't change, the content pool grows.
+
+---
+
+## Open Questions for the Workshop
+
+These are the decisions we need to make or at least directionally resolve:
+
+### Architecture
+1. **Template granularity:** How big is a Tier 2 template? A single building? A district? An entire station? What's the atomic unit?
+2. **Instantiation timing:** How far ahead of the player do we generate Tier 2 content? One system away? When they buy a ticket? When they hear a rumor?
+3. **Persistence vs. disposal:** Once generated, does Tier 2 content persist forever or can it be recycled if the player leaves and doesn't return? What are the rules? Does the player's home system have different persistence rules?
+4. **Cross-template connections:** How do Tier 2 templates reference each other? Can a smuggling ring in System A have a supplier in System B's black market template? How complex do we let the web get?
+
+### Simulation
+5. **NPC memory and continuity:** If a player meets an NPC, leaves for 10 hours of gameplay, and returns — what has that NPC been doing? What's the minimum background simulation to feel alive?
+6. **Simulation budget:** How many NPCs can we sustain in Background tier? What tick rate? What's the ceiling before performance degrades?
+7. **Life system depth:** How deep do we go on jobs, housing, relationships? Stardew Valley depth? Dwarf Fortress depth? Something in between? What's the minimum that doesn't feel like a gimmick?
+
+### Storyteller & Drama
+8. **Storyteller scope:** The storyteller paces events and activates Tier 1 modules. Does it also control Tier 2 instantiation? Life events? Relationship developments?
+9. **Module interaction:** Can two Tier 1 modules conflict with or reinforce each other? What happens when the conspiracy the player is investigating collides with the faction war they've been ignoring?
+10. **Player agency vs. storyteller control:** If the player wants to live a quiet life, how aggressively does the storyteller push drama? Can the player opt out of escalation? Should they be able to?
+
+### Content & Authoring
+11. **Character perspective variation:** Same Tier 2 template, different playable character. How much changes? Just access and knowledge, or does the template itself vary?
+12. **Scope and authoring pipeline:** Who writes Tier 2 templates? What's the format? How do we test them in isolation? What tooling do we need?
+13. **Quality floor:** What's the minimum viable Tier 3? How much ambient detail before a location feels dead? Can we define a measurable standard?
+14. **Dialogue architecture:** How does dialogue work for generated NPCs across both investigation and social play? Branching trees per template? Systemic dialogue driven by NPC axes? LLM-assisted? What's the authoring model?
+
+### DLC & Longevity
+15. **Base game scope:** How many Tier 1 modules ship in the base game? How many Tier 2 templates? What's the minimum complete experience?
+16. **DLC boundaries:** What constitutes a DLC pack? A new Tier 1 module? A region? A character? A life path? What's the right granularity for paid content?
+17. **Template interface stability:** If DLC adds to the pool, how do we version template interfaces so old saves don't break? What's the contract between a template and the engine?
+18. **Modding:** If templates have a standardized format, do we open it to modders? When? Community-authored Tier 2 templates could massively extend longevity.
+
+### Vertical Slice
+19. **First playable target:** Which 15–20 Tier 2 templates do we build first? Must include both intrigue and life templates. What's the minimum that proves the full loop?
+20. **Proof of concept:** What's the single most important thing to prove — that the life sim works, that conspiracies activate naturally, that generated NPCs feel real, or that the tiers interlock? Pick one for the first milestone.
+
+---
+
+## Preparation
+
+Before the workshop, consider:
+
+- **MIRI:** What world-building constraints affect template design? Which location types must exist for the setting to feel real? What does "daily life in the Settled Reach" look like for ordinary people — not just investigators and politicians?
+- **OZZIE:** What makes a procedurally assembled location feel like a discovery? Where are the wow-moment opportunities in *mundane* life, not just intrigue? What makes a player care about their apartment?
+- **PAULA:** How do NPC relationship webs sustain narrative depth when most characters are generated? What's the minimum for political intrigue to work? What makes a generated romantic interest feel like a person and not a dating sim menu?
+- **GORE:** How does the ascension/intelligence theme thread through generated content? Does the life sim layer connect to the game's deeper themes or is it purely systemic? Can "living a life" be thematically meaningful?
+- **GESTALT:** What systemic interactions between NPC axes create the most interesting gameplay? Which axes are essential vs. nice-to-have? How do life systems (economy, housing, social) create interesting decisions without becoming spreadsheet management?
+- **NIGEL:** What makes a second playthrough feel different? If a player lived as a cop first and replays as a bartender, what changes at the Tier 2 level? How do life paths create replayability beyond "different starting stats"?
+- **TYRE:** What are the hard technical constraints on NPC count, simulation tiers, and instantiation speed? What's the Background tier performance envelope? What does DLC module loading look like technically?
+- **MELLANIE:** What does an authored Tier 2 template look like as a writing deliverable — for both intrigue and life templates? How do we write dialogue that works across randomized NPC traits? What's the minimum authored text per template for NPCs to not sound hollow? How does romantic/social dialogue differ from investigation dialogue in terms of authoring needs?
+
+---
+
+## Success Criteria
+
+After the workshop we should have:
+
+- Agreement on the three-tier model (with life sim substrate) or a better alternative
+- Directional agreement on the Tier 1 pool approach (conspiracies as optional, plural modules)
+- Defined atomic unit for Tier 2 templates
+- Agreed NPC axis list (final or near-final, including social/romantic axes)
+- Rough scope numbers: how many templates per type, how many NPC axes, how much Tier 3 detail
+- Simulation tier boundaries defined (Active / Background / Dormant / Ungenerated)
+- Technical constraints documented by TYRE
+- DLC architecture principles agreed (or flagged for a dedicated follow-up session)
+- A path toward vertical slice template selection
+- Decision on proof-of-concept priority (question 20)
+- Enough clarity for SI to create workstreams
+
+---
+
+*This brief captures the strategic direction discussed in pre-workshop planning. All specifics are starting positions for debate, not decisions.*